Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revisionNext revisionBoth sides next revision | ||
jobs [2014/04/15 15:48] – [Theses and Jobs] jworch | jobs [2015/09/08 12:24] – [Theses and Jobs] nyga | ||
---|---|---|---|
Line 3: | Line 3: | ||
If you are looking for a bachelor/ | If you are looking for a bachelor/ | ||
- | == Web-based knowledge visualizations (BA/HiWi) == | ||
- | {{ : | ||
- | The knowledge base visualization allows to display semantic environment maps, | + | == Kitchen Activity Games in a Realistic Robotic Simulator (BA/MA/HiWi)== |
- | objects, human poses, trajectories and similar information stored | + | {{ :research:gz_env1.png?200|}} |
- | robot' | + | |
- | is written in Java and has grown old over the years. Recently, there has been | + | |
- | much progress in creating [[http:// | + | |
- | 3D visualizations]] for ROS that can also be accessed with a | + | |
- | [[http://www.ros.org/ | + | |
- | a web-based version of the visualization using these techniques. | + | |
- | Requirements: | + | Developing new activities and improving the current simulation framework done under the [[http:// |
- | * Good programming skills | + | |
- | * Experience with JavaScript development | + | |
- | * Knowledge of Web technologies (HTML, XML, OWL) | + | |
- | Contact: [[team: | + | Requirements: |
+ | * Good programming skills in C/C++ | ||
+ | * Basic physics/ | ||
+ | * Gazebo simulator basic tutorials | ||
+ | Contact: [[team: | ||
- | == Tools for knowledge acquisition from the Web (BA/MA/HiWi) == | + | == Integrating Eye Tracking in the Kitchen Activity Games (BA/MA)== |
+ | {{ : | ||
- | There are several options for doing a project related to the acquisition | + | Integrating |
- | knowledge from Web sources like online shops, repositories of object models, | + | |
- | recipe databases, etc. | + | |
Requirements: | Requirements: | ||
- | * Programing | + | * Good programming |
- | * Experience with Web languages and datamining techniques is helpful | + | * Gazebo simulator basic tutorials |
- | * Depending on the focus of the project, experience with database technology, natural-language processing or computer vision may be helpful | + | |
- | Contact: [[team:moritz_tenorth|Moritz Tenorth]] | + | Contact: [[team:andrei_haidu|Andrei Haidu]] |
+ | == Hand Skeleton Tracking Using Two Leap Motion Devices (BA/MA)== | ||
+ | {{ : | ||
- | == GPU-based Parallelization of Numerical Optimization Techniques (BA/MA/HiWi)== | + | Improving the skeletal tracking offered by the [[https://developer.leapmotion.com/ |
- | In the field of Machine Learning, numerical optimization techniques play a focal role. However, | + | The tracked hand can then be used as input for the Kitchen Activity Games framework. |
Requirements: | Requirements: | ||
- | | + | * Good programming skills in C/C++ |
- | | + | |
- | Contact: [[team:daniel_nyga|Daniel Nyga]] | + | Contact: [[team:andrei_haidu|Andrei Haidu]] |
- | == Online Learning of Markov Logic Networks for Natural-Language Understanding | + | == Fluid Simulation in Gazebo |
+ | {{ : | ||
- | Markov Logic Networks | + | [[http:// |
- | Requirements: | + | Currently there is an [[http:// |
- | * Experience | + | |
- | * Experience with statistical relational learning (e.g. MLNs) is helpful. | + | |
- | * Good programming skills in Python. | + | |
- | Contact: [[team: | + | The computational method for the fluid simulation is SPH (Smoothed-particle Dynamics), however newer and better methods based on SPH are currently present |
+ | and should be implemented (PCISPH/ | ||
+ | The interaction between the fluid and the rigid objects is a naive one, the forces and torques are applied only from the particle collisions (not taking into account pressure and other forces). | ||
- | ==HiWi-Position: Knowledge Representation & Language Understanding for Intelligent Robots== | + | Another topic would be the visualization of the fluid, currently is done by rendering every particle. For the rendering engine [[http:// |
- | In the context of the European research project RoboHow.Cog | + | Here is a [[https:// |
- | are investigating methods for combining multimodal sources of knowledge (e.g. video, natural-language recipes or computer games), | + | |
- | The Institute for Artificial Intelligence is hiring a student researcher for the | + | Requirements: |
- | development and the integration of probabilistic methods | + | * Good programming skills |
+ | * Interest in Fluid simulation | ||
+ | * Basic physics/ | ||
+ | * Gazebo simulator | ||
- | This HiWi-Position can serve as a starting point for future Bachelor' | + | Contact: [[team: |
- | Tasks: | ||
- | * Implementation of an interface to the Robot Operating System (ROS). | ||
- | * Linkage of the knowledge base to the executive of the robot. | ||
- | * Support for the scientific staff in extending and integrating components onto the robot platform PR2. | ||
- | Requirements: | + | == Automated sensor calibration toolkit |
- | * Studies in Computer Science | + | |
- | * Basic skills in Artificial Intelligence | + | |
- | * Optional: basic skills in Probability Theory | + | |
- | * Optional: basic skills in Machine Learning | + | |
- | * Good programming skills in Python and Java | + | |
- | Hours: 10-20 h/week | + | Computer vision is an important part of autonomous robots. For robots the image sensors are the main source of information of the surrounding world. Each camera is different, even if they are from the same production line. For computer vision, especially for robots manipulating their environment, |
- | Contact: [[team: | + | The topic for this thesis is to develop an automated system for calibrating cameras, especially RGB-D cameras like the Kinect v2. |
- | [1] www.robohow.eu\\ | + | {{ : |
- | [2] http:// | + | The system should: |
+ | * be independent of the camera type | ||
+ | * estimate intrinsic and extrinsic parameters | ||
+ | * calibrate depth images (case of RGB-D) | ||
+ | * integrate capabilities from Halcon | ||
+ | * operate autonomously | ||
- | == HiWi position: Segmentation | + | Requirements: |
+ | * Good programming skills in Python | ||
+ | * ROS, OpenCV | ||
- | {{ :research: | + | [1] http:// |
- | Competent object interaction requires knowledge about the structure | + | Contact: [[team: |
- | composition of objects. In an ongoing research project, we are investigating | + | |
- | how part-based object models can automatically be extracted from CAD models | + | |
- | found on the Web, e.g. on the [[http:// | + | |
- | We are looking for a student research assistant to push this topic forward. | + | == On-the-fly 3D CAD model creation (MA)== |
- | In close collaboration with the researchers of the Institute for Artificial | + | |
- | Intelligence, | + | |
- | segmentation, | + | |
- | methods into the robot' | + | |
- | the segmentation results. Depending on the results, cooperation on joint | + | |
- | publications may be possible. | + | |
- | This HiWi position can serve as a starting point for future Bachelor' | + | Create models during runtime |
- | Master' | + | |
- | project that could be worked on as a Master' | + | |
- | Requirements: | + | Requirements: |
- | * Good Java programming skills | + | * Good programming skills |
- | * Basic knowledge of 3D geometry calculations | + | * strong background in computer vision |
- | * Experience with working with 3D models is helpful | + | * ROS, OpenCV, PCL |
- | Contact: [[team:moritz_tenorth|Moritz Tenorth]] | + | Contact: [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]] |
- | == Depth-Adaptive Superpixels | + | == Simulation of a robots belief state to support perception(MA) == |
- | We are currently investigating | + | Create |
- | Since the current implementation of DASP is not very performant for high resolution images, there are several possibilities options for doing a project | + | Requirements: |
+ | * Good programming skills in C/C++ | ||
+ | * strong background | ||
+ | * Gazebo, OpenCV, PCL | ||
- | Requirements: | + | Contact: [[team: |
- | * Basic knowledge | + | |
- | * Good programming skills in C/C++. | + | == Multi-expert segmentation |
- | * Experience with CUDA is helpful | + | |
+ | Objects in a human environment are usually found in challenging scenes. They can be stacked upon eachother, touching or occluding, can be found in drawers, cupboards, refrigerators and so on. A personal robot assistant in order to execute a task, needs to detect these objects and recognize them. In this thesis a multi-modal approach to interpreting cluttered scenes is going to be investigated, | ||
+ | |||
+ | Requirements: | ||
+ | * Good programming skills in C/C++ | ||
+ | * strong background in 3D vision | ||
+ | * basic knowledge of ROS, OpenCV, PCL | ||
- | Contact: [[team:jan-hendrik_worch|Jan-Hendrik Worch]] | + | Contact: [[team:ferenc_balint-benczedi|Ferenc Balint-Benczedi]] |
Prof. Dr. hc. Michael Beetz PhD
Head of Institute
Contact via
Andrea Cowley
assistant to Prof. Beetz
ai-office@cs.uni-bremen.de
Discover our VRB for innovative and interactive research
Memberships and associations: